peter65374 / openbuddy-mistral-7b

Openbuddy finetuned mistral-7b in GPTQ quantization in 4bits by TheBloke

  • Public
  • 69 runs
  • L40S
  • GitHub
  • License
Iterate in playground

Input

*string
Shift + Return to add a new line
integer
(minimum: 1, maximum: 3500)

The maximum number of tokens the model should generate as output.

Default: 1024

number

The value used to modulate the next token probabilities.

Default: 0.7

number
(minimum: 0.01, maximum: 1)

A probability threshold for generating the output. If < 1.0, only keep the top tokens with cumulative probability >= top_p (nucleus filtering). Nucleus filtering is described in Holtzman et al. (http://arxiv.org/abs/1904.09751).

Default: 0.95

integer
(minimum: 1, maximum: 100)

The number of highest probability tokens to consider for generating the output. If > 0, only keep the top k tokens with highest probability (top-k filtering).

Default: 40

boolean

Whether or not to use sampling ; use greedy decoding otherwise.

Default: true

integer
(minimum: 1, maximum: 10)

Number of beams for beam search. 1 means no beam search.

Default: 1

number
(minimum: 0.01, maximum: 5)

Repetition penalty, (float, *optional*, defaults to 1.0): The parameter for repetition penalty. 1.0 means no penalty. values greater than 1 discourage repetition, less than 1 encourage it. See [this paper](https://arxiv.org/pdf/1909.05858.pdf) for more details.

Default: 1

string
Shift + Return to add a new line

The template used to format the prompt. The input prompt is inserted into the template using the `{prompt}` placeholder.

Default: "You are a helpful high school Math tutor. If you don't know the answer to a question, please don't share false information. You can speak fluently in many languages.\nUser: Hi\nAssistant: Hello, how can I help you?</s>\nUser: {prompt}\nAssistant:"

boolean

Whether to pad the left side of the prompt with eos token.

Default: true

string
Shift + Return to add a new line

A comma-separated list of sequences to stop generation at. For example, '<end>,<stop>' will stop generation at the first instance of 'end' or '<stop>'.

boolean

provide debugging output in logs

Default: false

Output

好的,让我们来看一下这道题。 题目要求我们计算一个球是红色,另一个球是蓝色的概率。这个问题可以通过条件概率公式来解决。 我们可以先抽出红球,然后再抽出蓝球,也可以先抽出蓝球,然后再抽出红球。所以,我们需要把这两种情况的概率加起来。 如果我们先抽出红球,然后再抽出蓝球,那么这两次抽球的概率分别是 (4/10) 和 (6/9)。这时候,我们需要将它们相乘,得到的结果是 (4/10)*(6/9) = 24/90 = 4/15。 如果我们先抽出蓝球,然后再抽出红球,那么这两次抽球的概率分别是 (6/10) 和 (4/9)。这时候,我们同样需要将它们相乘,得到的结果是 (6/10)*(4/9) = 24/90 = 4/15。 最后,我们将这两种情况的概率相加,得到的结果是 (4/15) + (4/15) = 8/15。 所以,一个球是红色,另一个球是蓝色的概率是 8/15。
Generated in

Run time and cost

This model costs approximately $0.061 to run on Replicate, or 16 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia L40S GPU hardware. Predictions typically complete within 63 seconds. The predict time for this model varies significantly based on the inputs.

Readme

This is a Cog implementation test for Language model streaming. The model is from Openbuddy finetuned mistral-7b in GPTQ quantization in 4bits by TheBloke.